Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5987 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1326903 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0492. Min Act: -0.0002

Data Index: 168392 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0468. Min Act: -0.0002

Data Index: 717071 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0438. Min Act: -0.0002

Data Index: 86966 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0436. Min Act: -0.0002

Data Index: 159261 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0467. Min Act: -0.0002

Data Index: 1138944 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0456. Min Act: -0.0002

Data Index: 331418 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1369144 (Python Code)

Max Activating Token Index: 665

Text #8

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1018037 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1073695 (C4 (Web Text))

Max Activating Token Index: 374

Text #10

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0440. Min Act: -0.0002

Data Index: 791745 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0447. Min Act: -0.0002

Data Index: 1260446 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0413. Min Act: -0.0002

Data Index: 367170 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0417. Min Act: -0.0002

Data Index: 213960 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0435. Min Act: -0.0002

Data Index: 17886 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0454. Min Act: -0.0002

Data Index: 231369 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0418. Min Act: -0.0002

Data Index: 437012 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0394. Min Act: -0.0002

Data Index: 1440947 (Python Code)

Max Activating Token Index: 830

Text #18

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1532936 (Python Code)

Max Activating Token Index: 16

Text #19

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0381. Min Act: -0.0002

Data Index: 375295 (C4 (Web Text))

Max Activating Token Index: 528